Model reduction and optimization of reactive batch distillation based on the adaptive neuro-fuzzy inference system and differential evolution

Abstract

This paper considers the application of the adaptive neuro-fuzzy inference system (ANFIS) instead of the highly nonlinear model of a reactive batch distillation column for optimization. The architecture has been developed for fuzzy modeling that learns information from a data set, in order to compute the membership function and rule base in accordance with the given input-output data. In this work, the differential evolution algorithm has been employed for optimization of operation policy of reactive batch distillation for producing ethyl acetate. In optimization, minimal batch time and high purity of product are considered, and reflux ratio and final batch time are taken as decision parameters. The results show that the reduced model (ANFIS) is able to properly create a robust model of the reactive batch distillation, and CPU use is reduced to 1/18,000 of that of a real mathematical model. The highest yield and mole fraction of ethyl acetate were achieved through the use of the obtained optimization policy.

Hybridized neural fuzzy ensembles for dust source modeling and prediction

“…Some researchers believe that the main reason for its strength is its design principles (simplicity, efficiency, and real coding) (Noman and Iba, 2008;Price, 2013;Das et al, 2016). As discussed by Khazraee et al (2011), the use of the differential evolution (DE) algorithm is likely to generate a more robust and efficient optimization tool for any predictive model, given its ability to perform a direct search of data features without requiring any derivative estimation or assumptions. This explains the enhanced performance capability of the ANFIS-DE hybridized model.…”

A fractional order fuzzy PID controller for binary distillation column control

“…The highest yield and mole fraction of ethyl acetate was claimed to be achieved through the use of the obtained optimization policy. It was also claimed that reduced model (ANFIS) was able to reduce CPU use up to 1/18,000 times that of a real mathematical model (Khazraee, Jahanmiri, & Ghorayshi, 2010). Moghadam et al proposed the application of LQR for controlling concentration profiles along a catalytic distillation column (Moghadam et al, 2011).…”

Training ANFIS by using the artificial bee colony algorithm

“…Jalali-Heravi and Asadollahi-Baboli [8] suggested modified ant colony algorithm-based ANFIS training for the prediction of the inhibitory activity of quinazolinone derivatives on serotonin. Khazraee et al [9] trained ANFIS with a differential evolution for model reduction and optimization of reactive batch distillation. Priyadharsini et al [10] proposed an artifact removal study based on ANFIS and used an artificial immune algorithm to optimize the parameters of ANFIS.…”